Search Results for author: Zhe Li

Found 119 papers, 49 papers with code

RFBFN: A Relation-First Blank Filling Network for Joint Relational Triple Extraction

1 code implementation ACL 2022 Zhe Li, Luoyi Fu, Xinbing Wang, Haisong Zhang, Chenghu Zhou

However, most existing works either ignore the semantic information of relations or predict subjects and objects sequentially.

Relation

Low-Resource Text Classification via Cross-lingual Language Model Fine-tuning

no code implementations CCL 2020 Xiuhong Li, Zhe Li, Jiabao Sheng, Wushour Slamu

There are major challenges of low-resource agglutinative text classification the lack of labeled data in a target domain and morphologic diversity of derivations in language structures.

Language Modeling Language Modelling +3

Semantically Robust Unsupervised Image Translation for Paired Remote Sensing Images

no code implementations17 Feb 2025 Sheng Fang, Kaiyu Li, Zhe Li, Jianli Zhao, Xingli Zhang

Image translation for change detection or classification in bi-temporal remote sensing images is unique.

Scaling Pre-training to One Hundred Billion Data for Vision Language Models

no code implementations11 Feb 2025 Xiao Wang, Ibrahim Alabdulmohsin, Daniel Salz, Zhe Li, Keran Rong, Xiaohua Zhai

We provide an empirical investigation of the potential of pre-training vision-language models on an unprecedented scale: 100 billion examples.

Diversity

Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization

no code implementations4 Feb 2025 Yixiao Chen, Shikun Sun, Jianshu Li, Ruoyu Li, Zhe Li, Junliang Xing

Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial.

Spectral-Aware Low-Rank Adaptation for Speaker Verification

1 code implementation7 Jan 2025 Zhe Li, Man-Wai Mak, Mert Pilanci, Hung-Yi Lee, Helen Meng

Previous research has shown that the principal singular vectors of a pre-trained model's weight matrices capture critical knowledge.

parameter-efficient fine-tuning Speaker Verification

Inclusion 2024 Global Multimedia Deepfake Detection: Towards Multi-dimensional Facial Forgery Detection

no code implementations30 Dec 2024 Yi Zhang, Weize Gao, Changtao Miao, Man Luo, Jianshu Li, Wenzhong Deng, Zhe Li, Bingyu Hu, Weibin Yao, Wenbo Zhou, Tao Gong, Qi Chu

In this paper, we present the solutions from the top 3 teams of the two tracks, to boost the research work in the field of image and audio-video forgery detection.

DeepFake Detection Face Swapping +1

MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation

no code implementations18 Dec 2024 Shenhao Zhu, Lingteng Qiu, Xiaodong Gu, Zhengyi Zhao, Chao Xu, Yuxiao He, Zhe Li, Xiaoguang Han, Yao Yao, Xun Cao, Siyu Zhu, Weihao Yuan, Zilong Dong, Hao Zhu

In the generation stage, we adopt a Diffusion Transformer (DiT) model to generate PBR materials, where both the specially designed multi-branch DiT and reference-based DiT blocks adopt a global attention mechanism to promote feature interaction and fusion between different views, thereby improving multi-view consistency.

Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models

1 code implementation18 Dec 2024 Zheng Hu, Zhe Li, Ziyun Jiao, Satoshi Nakagawa, Jiawen Deng, Shimin Cai, Tao Zhou, Fuji Ren

In recent years, knowledge graphs have been integrated into recommender systems as item-side auxiliary information, enhancing recommendation accuracy.

Contrastive Learning Knowledge Graphs +3

MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow

no code implementations13 Dec 2024 Zhe Li, Yisheng He, Lei Zhong, Weichao Shen, Qi Zuo, Lingteng Qiu, Zilong Dong, Laurence Tianruo Yang, Weihao Yuan

Generating motion sequences conforming to a target style while adhering to the given content prompts requires accommodating both the content and style.

Contrastive Learning Motion Generation

A Compact Hybrid Battery Thermal Management System for Enhanced Cooling

no code implementations1 Dec 2024 Zhipeng Lyu, Jinrong Su, Zhe Li, Xiang Li, Hanghang Yan, Lei Chen

Hybrid battery thermal management systems (HBTMS) combining active liquid cooling and passive phase change materials (PCM) cooling have shown a potential for the thermal management of lithium-ion batteries.

Management

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models

1 code implementation1 Oct 2024 Wei Zhao, Zhe Li, Yige Li, Jun Sun

First, we demonstrate that benign features can be effectively made to function as adversarial suffixes, i. e., we develop a feature extraction method to extract sample-agnostic features from benign dataset in the form of suffixes and show that these suffixes may effectively compromise safety alignment.

Safety Alignment

Do Influence Functions Work on Large Language Models?

1 code implementation30 Sep 2024 Zhe Li, Wei Zhao, Yige Li, Jun Sun

Influence functions are important for quantifying the impact of individual training data points on a model's predictions.

Data-Efficient Generation for Dataset Distillation

no code implementations5 Sep 2024 Zhe Li, Weitong Zhang, Sarah Cechnicka, Bernhard Kainz

While deep learning techniques have proven successful in image-related tasks, the exponentially increased data storage and computation costs become a significant challenge.

Dataset Distillation

Orca: Ocean Significant Wave Height Estimation with Spatio-temporally Aware Large Language Models

no code implementations29 Jul 2024 Zhe Li, Ronghui Xu, Jilin Hu, Zhong Peng, Xi Lu, Chenjuan Guo, Bin Yang

By segmenting the limited buoy observational data temporally, encoding the buoys' locations spatially, and designing prompt templates, Orca capitalizes on the robust generalization ability of LLMs to estimate significant wave height effectively with limited data.

Dreamer: Dual-RIS-aided Imager in Complementary Modes

1 code implementation20 Jul 2024 Fuhai Wang, Yunlong Huang, Zhanbo Feng, Rujing Xiong, Zhe Li, Chun Wang, Tiebin Mi, Robert Caiming Qiu, Zenan Ling

Reconfigurable intelligent surfaces (RISs) have emerged as a promising auxiliary technology for radio frequency imaging.

SSIM

MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos

1 code implementation11 Jul 2024 Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, Yebin Liu

We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos.

NeRF

PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation

1 code implementation28 Jun 2024 Zhangjing Yang, Dun Liu, Xin Wang, Zhe Li, Barathwaj Anandan, Yi Wu

This method achieves high video instance segmentation performance without manual video annotations, offering a cost-effective solution and new perspectives for video instance segmentation applications.

Instance Segmentation Segmentation +2

Subtractive Training for Music Stem Insertion using Latent Diffusion Models

no code implementations27 Jun 2024 Ivan Villa-Renteria, Mason L. Wang, Zachary Shah, Zhe Li, Soohyun Kim, Neelesh Ramachandran, Mert Pilanci

We also show that we can use the text instruction to control the generation of the inserted stem in terms of rhythm, dynamics, and genre, allowing us to modify the style of a single instrument in a full song while keeping the remaining instruments the same.

Image Distillation for Safe Data Sharing in Histopathology

1 code implementation19 Jun 2024 Zhe Li, Bernhard Kainz

We train a latent diffusion model and construct a new distilled synthetic dataset with a small number of human readable synthetic images.

Dataset Distillation Prognosis

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?

1 code implementation3 Jun 2024 Guanhua Huang, Yuchen Zhang, Zhe Li, Yongjian You, Mingze Wang, Zhouwang Yang

The SCRN employs a reconstruction network to add and remove noise from text, extracting a semantic representation that is robust to local perturbations.

Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing

1 code implementation28 May 2024 Wei Zhao, Zhe Li, Yige Li, Ye Zhang, Jun Sun

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications.

Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization

1 code implementation24 May 2024 Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, Haibo Yang

This paper proposes a novel dimension-free communication algorithm - DeComFL, which leverages the zeroth-order optimization techniques and reduces the communication cost from $\mathscr{O}(d)$ to $\mathscr{O}(1)$ by transmitting only a constant number of scalar values between clients and the server in each round, regardless of the dimension $d$ of the model parameters.

Classification Federated Learning +2

LayGA: Layered Gaussian Avatars for Animatable Clothing Transfer

no code implementations12 May 2024 Siyou Lin, Zhe Li, Zhaoqi Su, Zerong Zheng, Hongwen Zhang, Yebin Liu

In the single-layer reconstruction stage, we propose a series of geometric constraints to reconstruct smooth surfaces and simultaneously obtain the segmentation between body and clothing.

Virtual Try-on

Automatic Knowledge Graph Construction for Judicial Cases

no code implementations15 Apr 2024 Jie zhou, Xin Chen, Hang Zhang, Zhe Li

Building on these results, we detail the automatic construction process of case knowledge graphs for judicial cases, enabling the assembly of knowledge graphs for hundreds of thousands of judgments.

graph construction Knowledge Graphs

MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion

1 code implementation12 Apr 2024 Zhe Li, Haiwei Pan, Kejia Zhang, Yuhua Wang, Fengming Yu

Multi-modality image fusion (MMIF) aims to integrate complementary information from different modalities into a single fused image to represent the imaging scene and facilitate downstream visual tasks comprehensively.

Image Reconstruction Mamba +2

TexVocab: Texture Vocabulary-conditioned Human Avatars

no code implementations CVPR 2024 Yuxiao Liu, Zhe Li, Yebin Liu, Haoqian Wang

To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation.

Human Dynamics

Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling

no code implementations1 Mar 2024 shiyi qi, Liangjian Wen, Yiduo Li, Yuanhang Yang, Zhe Li, Zhongwen Rao, Lujia Pan, Zenglin Xu

To substantiate this claim, we introduce the Cross-variable Decorrelation Aware feature Modeling (CDAM) for Channel-mixing approaches, aiming to refine Channel-mixing by minimizing redundant information between channels while enhancing relevant mutual information.

Multivariate Time Series Forecasting Time Series

Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learning

no code implementations3 Feb 2024 Zhe Li, Ziyang Zhang, Jinglin Zhao, Zheng Wang, Bocheng Ren, Debin Liu, Laurence T. Yang

Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models and effectively addresses the issue of information leakage.

MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning

no code implementations CVPR 2024 Zhe Li, Laurence T. Yang, Bocheng Ren, Xin Nie, Zhangyang Gao, Cheng Tan, Stan Z. Li

The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning.

Contrastive Learning Image Classification +5

Widely Linear Matched Filter: A Lynchpin towards the Interpretability of Complex-valued CNNs

no code implementations30 Jan 2024 Qingchen Wang, Zhe Li, Zdenka Babic, Wei Deng, Ljubiša Stanković, Danilo P. Mandic

However, applying this paradigm to illuminate the interpretability of complex-valued CNNs meets a formidable obstacle: the extension of matched filtering to a general class of noncircular complex-valued data, referred to here as the widely linear matched filter (WLMF), has been only implicit in the literature.

General Point Model Pretraining with Autoencoding and Autoregressive

1 code implementation CVPR 2024 Zhe Li, Zhangyang Gao, Cheng Tan, Bocheng Ren, Laurence T. Yang, Stan Z. Li

Compared to models like Point-BERT MaskPoint and PointMAE our GPM achieves superior performance in point cloud understanding tasks.

Decoder Language Modeling +5

Causality Analysis for Evaluating the Security of Large Language Models

1 code implementation13 Dec 2023 Wei Zhao, Zhe Li, Jun Sun

Based on a layer-level causality analysis, we show that RLHF has the effect of overfitting a model to harmful prompts.

Red Teaming

HHAvatar: Gaussian Head Avatar with Dynamic Hairs

1 code implementation CVPR 2024 Zhanfeng Liao, Yuelang Xu, Zhe Li, Qijing Li, Boyao Zhou, Ruifeng Bai, Di Xu, Hongwen Zhang, Yebin Liu

To address the problem of dynamic hair modeling, we introduce a hybrid head model into our avatar representation based Gaussian Head Avatar and a training method that considers timing information and an occlusion perception module to model the non-rigid motion of hair.

2k

Animatable and Relightable Gaussians for High-fidelity Human Avatar Modeling

1 code implementation27 Nov 2023 Zhe Li, Yipengjing Sun, Zerong Zheng, Lizhen Wang, Shengping Zhang, Yebin Liu

To associate 3D Gaussians with the animatable avatar, we learn a parametric template from the input videos, and then parameterize the template on two front & back canonical Gaussian maps where each pixel represents a 3D Gaussian.

NeRF

Robust Learning Based Condition Diagnosis Method for Distribution Network Switchgear

no code implementations14 Nov 2023 Wenxi Zhang, Zhe Li, Weixi Li, Weisi Ma, Xinyi Chen, Sizhe Li

This paper introduces a robust, learning-based method for diagnosing the state of distribution network switchgear, which is crucial for maintaining the power quality for end users.

Position

General Point Model with Autoencoding and Autoregressive

no code implementations25 Oct 2023 Zhe Li, Zhangyang Gao, Cheng Tan, Stan Z. Li, Laurence T. Yang

This model is versatile, allowing fine-tuning for downstream point cloud representation tasks, as well as unconditional and conditional generation tasks.

Decoder Language Modeling +5

Whole Slide Multiple Instance Learning for Predicting Axillary Lymph Node Metastasis

1 code implementation6 Oct 2023 Glejdis Shkëmbi, Johanna P. Müller, Zhe Li, Katharina Breininger, Peter Schüffler, Bernhard Kainz

Breast cancer is a major concern for women's health globally, with axillary lymph node (ALN) metastasis identification being critical for prognosis evaluation and treatment guidance.

Data Augmentation Multiple Instance Learning +2

Inferring Inference

1 code implementation4 Oct 2023 Rajkumar Vasudeva Raju, Zhe Li, Scott Linderman, Xaq Pitkow

Given a time series of neural activity during a perceptual inference task, our framework finds (i) the neural representation of relevant latent variables, (ii) interactions between these variables that define the brain's internal model of the world, and (iii) message-functions specifying the inference algorithm.

Experimental Design

A Graph Reconstruction by Dynamic Signal Coefficient for Fault Classification

no code implementations30 May 2023 Wenbin He, Jianxu Mao, Yaonan Wang, Zhe Li, Qiu Fang, Haotian Wu

To improve the performance in identifying the faults under strong noise for rotating machinery, this paper presents a dynamic feature reconstruction signal graph method, which plays the key role of the proposed end-to-end fault diagnosis model.

Fault Diagnosis feature selection +1

Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping

1 code implementation18 May 2023 Zhe Li, shiyi qi, Yiduo Li, Zenglin Xu

In this paper, we thoroughly investigate the intrinsic effectiveness of recent approaches and make three key observations: 1) linear mapping is critical to prior long-term time series forecasting efforts; 2) RevIN (reversible normalization) and CI (Channel Independent) play a vital role in improving overall forecasting performance; and 3) linear mapping can effectively capture periodic features in time series and has robustness for different periods across channels when increasing the input horizon.

Time Series Time Series Forecasting

Caption Anything: Interactive Image Description with Diverse Multimodal Controls

1 code implementation4 May 2023 Teng Wang, Jinrui Zhang, Junjie Fei, Hao Zheng, Yunlong Tang, Zhe Li, Mingqi Gao, Shanshan Zhao

Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\textit{e. g.}$, looking at the specified regions or telling in a particular text style.

controllable image captioning Instruction Following

PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling

1 code implementation25 Apr 2023 Zhe Li, Zerong Zheng, Yuxiao Liu, Boyao Zhou, Yebin Liu

To this end, we present PoseVocab, a novel pose encoding method that encourages the network to discover the optimal pose embeddings for learning the dynamic human appearance.

Track Anything: Segment Anything Meets Videos

1 code implementation24 Apr 2023 Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, Feng Zheng

Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos.

Image Segmentation Segmentation +2

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

1 code implementation ICCV 2023 Zhendong Yang, Ailing Zeng, Zhe Li, Tianke Zhang, Chun Yuan, Yu Li

We decompose the KD loss and find the non-target loss from it forces the student's non-target logits to match the teacher's, but the sum of the two non-target logits is different, preventing them from being identical.

Self-Knowledge Distillation

Balancing Privacy Protection and Interpretability in Federated Learning

no code implementations16 Feb 2023 Zhe Li, Honglong Chen, Zhichen Ni, Huajie Shao

Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server, thereby potentially protecting users' private information.

Federated Learning

MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing

1 code implementation9 Feb 2023 Zhe Li, Zhongwen Rao, Lujia Pan, Zenglin Xu

Specifically, we find that (1) attention is not necessary for capturing temporal dependencies, (2) the entanglement and redundancy in the capture of temporal and channel interaction affect the forecasting performance, and (3) it is important to model the mapping between the input and the prediction sequence.

Multivariate Time Series Forecasting Time Series

Ti-MAE: Self-Supervised Masked Time Series Autoencoders

1 code implementation21 Jan 2023 Zhe Li, Zhongwen Rao, Lujia Pan, Pengyun Wang, Zenglin Xu

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios.

Contrastive Learning Multivariate Time Series Forecasting +2

Resource-Efficient RGBD Aerial Tracking

1 code implementation CVPR 2023 Jinyu Yang, Shang Gao, Zhe Li, Feng Zheng, Aleš Leonardis

However, current research on aerial perception has mainly focused on limited categories, such as pedestrian or vehicle, and most scenes are captured in urban environments from a birds-eye view.

Object Tracking

Learning Dual-Fused Modality-Aware Representations for RGBD Tracking

no code implementations6 Nov 2022 Shang Gao, Jinyu Yang, Zhe Li, Feng Zheng, Aleš Leonardis, Jingkuan Song

However, some existing RGBD trackers use the two modalities separately and thus some particularly useful shared information between them is ignored.

Object Tracking

Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space

no code implementations29 Oct 2022 Zhe Li, Man-Wai Mak, Helen Mei-Ling Meng

The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning.

Contrastive Learning Speaker Verification

Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability

1 code implementation29 Oct 2022 Zhe Li, Man-Wai Mak

A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains.

Contrastive Learning Data Augmentation +1

Changer: Feature Interaction is What You Need for Change Detection

1 code implementation17 Sep 2022 Sheng Fang, Kaiyu Li, Zhe Li

To verify the effectiveness of MetaChanger, we propose two derived models, ChangerAD and ChangerEx with simple interaction strategies: Aggregation-Distribution (AD) and "exchange".

Building change detection for remote sensing images Change Detection +1

Rethinking Knowledge Distillation via Cross-Entropy

1 code implementation22 Aug 2022 Zhendong Yang, Zhe Li, Yuan Gong, Tianke Zhang, Shanshan Lao, Chun Yuan, Yu Li

Furthermore, we smooth students' target output to treat it as the soft target for training without teachers and propose a teacher-free new KD loss (tf-NKD).

Knowledge Distillation

Prompting for Multi-Modal Tracking

no code implementations29 Jul 2022 Jinyu Yang, Zhe Li, Feng Zheng, Aleš Leonardis, Jingkuan Song

Multi-modal tracking gains attention due to its ability to be more accurate and robust in complex scenarios compared to traditional RGB-based tracking.

Rgb-T Tracking

AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture

1 code implementation5 Jul 2022 Zhe Li, Zerong Zheng, Hongwen Zhang, Chaonan Ji, Yebin Liu

Then given a monocular RGB video of this subject, our method integrates information from both the image observation and the avatar prior, and accordingly recon-structs high-fidelity 3D textured models with dynamic details regardless of the visibility.

Masked Generative Distillation

3 code implementations3 May 2022 Zhendong Yang, Zhe Li, Mingqi Shao, Dachuan Shi, Zehuan Yuan, Chun Yuan

The current distillation algorithm usually improves students' performance by imitating the output of the teacher.

Image Classification Instance Segmentation +5

RGBD Object Tracking: An In-depth Review

1 code implementation26 Mar 2022 Jinyu Yang, Zhe Li, Song Yan, Feng Zheng, Aleš Leonardis, Joni-Kristian Kämäräinen, Ling Shao

Particularly, we are the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking.

Object Object Tracking

SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text

no code implementations23 Feb 2022 Canjie Luo, Yuanzhi Zhu, Lianwen Jin, Zhe Li, Dezhi Peng

Specifically, we propose a style bank to parameterize the specific handwriting styles as latent vectors, which are input to a generator as style priors to achieve the corresponding handwritten styles.

Attribute Diversity +1

Learning Dynamics and Structure of Complex Systems Using Graph Neural Networks

no code implementations22 Feb 2022 Zhe Li, Andreas S. Tolias, Xaq Pitkow

In this work we trained graph neural networks to fit time series from an example nonlinear dynamical system, the belief propagation algorithm.

Inductive Bias Time Series +1

VRConvMF: Visual Recurrent Convolutional Matrix Factorization for Movie Recommendation

no code implementations16 Feb 2022 Zhu Wang, Honglong Chen, Zhe Li, Kai Lin, Nan Jiang, Feng Xia

Fortunately, context-aware recommender systems can alleviate the sparsity problem by making use of some auxiliary information, such as the information of both the users and items.

Descriptive Movie Recommendation +1

Edge Data Based Trailer Inception Probabilistic Matrix Factorization for Context-Aware Movie Recommendation

no code implementations16 Feb 2022 Honglong Chen, Zhe Li, Zhu Wang, Zhichen Ni, Junjian Li, Ge Xu, Abdul Aziz, Feng Xia

As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data.

Movie Recommendation Recommendation Systems

Focal and Global Knowledge Distillation for Detectors

1 code implementation CVPR 2022 Zhendong Yang, Zhe Li, Xiaohu Jiang, Yuan Gong, Zehuan Yuan, Danpei Zhao, Chun Yuan

Global distillation rebuilds the relation between different pixels and transfers it from teachers to students, compensating for missing global information in focal distillation.

Image Classification Knowledge Distillation +2

The emergence of cooperation from shared goals in the Systemic Sustainability Game of common pool resources

no code implementations1 Oct 2021 Chengyi Tu, Paolo DOdorico, Zhe Li, Samir Suweis

The sustainable use of common-pool resources (CPRs) is a major environmental governance challenge because of their possible over-exploitation.

Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras

no code implementations ICCV 2021 Yuxiang Zhang, Zhe Li, Liang An, Mengcheng Li, Tao Yu, Yebin Liu

Overall, we propose the first light-weight total capture system and achieves fast, robust and accurate multi-person total motion capture performance.

3D Multi-Person Pose Estimation

Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter

1 code implementation CVPR 2021 Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Dezhi Peng, Zhe Li, Mengchao He, Yongpan Wang, Canjie Luo

Specifically, we integrate IFA into the two most prevailing text recognition streams (attention-based and CTC-based) and propose attention-guided dense prediction (ADP) and Extended CTC (ExCTC).

Optical Character Recognition Optical Character Recognition (OCR) +1

Salient Positions based Attention Network for Image Classification

1 code implementation9 Jun 2021 Sheng Fang, Kaiyu Li, Zhe Li

Aimed at both questions this paper proposes the salient positions-based attention scheme SPANet, which is inspired by some interesting observations on the attention maps and affinity matrices generated in self-attention scheme.

Classification Image Classification

CARLS: Cross-platform Asynchronous Representation Learning System

1 code implementation26 May 2021 Chun-Ta Lu, Yun Zeng, Da-Cheng Juan, Yicheng Fan, Zhe Li, Jan Dlabal, Yi-Ting Chen, Arjun Gopalan, Allan Heydon, Chun-Sung Ferng, Reah Miyara, Ariel Fuxman, Futang Peng, Zhen Li, Tom Duerig, Andrew Tomkins

In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge makers and knowledge banks -- to concertedly work together in an asynchronous fashion across hardware platforms.

Representation Learning

ConTNet: Why not use convolution and transformer at the same time?

2 code implementations27 Apr 2021 Haotian Yan, Zhe Li, Weijian Li, Changhu Wang, Ming Wu, Chuang Zhang

It is also worth pointing that, given identical strong data augmentations, the performance improvement of ConTNet is more remarkable than that of ResNet.

Image Classification object-detection +1

Class-Incremental Learning with Generative Classifiers

2 code implementations20 Apr 2021 Gido M. van de Ven, Zhe Li, Andreas S. Tolias

As a proof-of-principle, here we implement this strategy by training a variational autoencoder for each class to be learned and by using importance sampling to estimate the likelihoods p(x|y).

class-incremental learning Class Incremental Learning +1

POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture

no code implementations CVPR 2021 Zhe Li, Tao Yu, Zerong Zheng, Kaiwen Guo, Yebin Liu

By contributing a novel reconstruction framework which contains pose-guided keyframe selection and robust implicit surface fusion, our method fully utilizes the advantages of both tracking-based methods and tracking-free inference methods, and finally enables the high-fidelity reconstruction of dynamic surface details even in the invisible regions.

3D Reconstruction

Temporal Action Segmentation from Timestamp Supervision

1 code implementation CVPR 2021 Zhe Li, Yazan Abu Farha, Juergen Gall

To demonstrate the effectiveness of timestamp supervision, we propose an approach to train a segmentation model using only timestamps annotations.

Action Segmentation Segmentation +2

Siamese NestedUNet Networks for Change Detection of High Resolution Satellite Image

1 code implementation27 Oct 2020 Kaiyu Li, Zhe Li, Sheng Fang

In this paper, we improve the semantic segmentation network UNet++ and propose a fully convolutional siamese network (Siam-NestedUNet) for change detection.

Change Detection Change detection for remote sensing images +2

Joint Multi-Dimension Pruning via Numerical Gradient Update

no code implementations18 May 2020 Zechun Liu, Xiangyu Zhang, Zhiqiang Shen, Zhe Li, Yichen Wei, Kwang-Ting Cheng, Jian Sun

To tackle these three naturally different dimensions, we proposed a general framework by defining pruning as seeking the best pruning vector (i. e., the numerical value of layer-wise channel number, spacial size, depth) and construct a unique mapping from the pruning vector to the pruned network structures.

Robust 3D Self-portraits in Seconds

no code implementations CVPR 2020 Zhe Li, Tao Yu, Chuanyu Pan, Zerong Zheng, Yebin Liu

In this paper, we propose an efficient method for robust 3D self-portraits using a single RGBD camera.

RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies

no code implementations7 Mar 2020 Zhe Li, Chunhua Sun, Chunli Liu, Xiayu Chen, Meng Wang, Yezheng Liu

To address these issues, we focus on semi-supervised outlier detection with few identified anomalies, in the hope of using limited labels to achieve high detection accuracy.

Outlier Detection

Long Short-Term Sample Distillation

no code implementations2 Mar 2020 Liang Jiang, Zujie Wen, Zhongping Liang, Yafang Wang, Gerard de Melo, Zhe Li, Liangzhuang Ma, Jiaxing Zhang, Xiaolong Li, Yuan Qi

The long-term teacher draws on snapshots from several epochs ago in order to provide steadfast guidance and to guarantee teacher--student differences, while the short-term one yields more up-to-date cues with the goal of enabling higher-quality updates.

CircConv: A Structured Convolution with Low Complexity

no code implementations28 Feb 2019 Siyu Liao, Zhe Li, Liang Zhao, Qinru Qiu, Yanzhi Wang, Bo Yuan

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications.

E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs

no code implementations12 Dec 2018 Zhe Li, Caiwen Ding, Siyue Wang, Wujie Wen, Youwei Zhuo, Chang Liu, Qinru Qiu, Wenyao Xu, Xue Lin, Xuehai Qian, Yanzhi Wang

It is a challenging task to have real-time, efficient, and accurate hardware RNN implementations because of the high sensitivity to imprecision accumulation and the requirement of special activation function implementations.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Adaptive Negative Curvature Descent with Applications in Non-convex Optimization

no code implementations NeurIPS 2018 Mingrui Liu, Zhe Li, Xiaoyu Wang, Jin-Feng Yi, Tianbao Yang

Negative curvature descent (NCD) method has been utilized to design deterministic or stochastic algorithms for non-convex optimization aiming at finding second-order stationary points or local minima.

Generative Adversarial Active Learning for Unsupervised Outlier Detection

2 code implementations28 Sep 2018 Yezheng Liu, Zhe Li, Chong Zhou, Yuanchun Jiang, Jianshan Sun, Meng Wang, Xiangnan He

In this paper, we approach outlier detection as a binary-classification issue by sampling potential outliers from a uniform reference distribution.

Active Learning Binary Classification +1

A Unified Analysis of Stochastic Momentum Methods for Deep Learning

no code implementations30 Aug 2018 Yan Yan, Tianbao Yang, Zhe Li, Qihang Lin, Yi Yang

However, their theoretical analysis of convergence of the training objective and the generalization error for prediction is still under-explored.

Deep Learning

EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch

no code implementations CVPR 2019 Jian Ren, Zhe Li, Jianchao Yang, Ning Xu, Tianbao Yang, David J. Foran

In this paper, we propose an Ecologically-Inspired GENetic (EIGEN) approach that uses the concept of succession, extinction, mimicry, and gene duplication to search neural network structure from scratch with poorly initialized simple network and few constraints forced during the evolution, as we assume no prior knowledge about the task domain.

An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints

no code implementations3 Jun 2018 Zhe Li, Xuehan Xiong, Zhou Ren, Ning Zhang, Xiaoyu Wang, Tianbao Yang

In this paper, we study how to design a genetic programming approach for optimizing the structure of a CNN for a given task under limited computational resources yet without imposing strong restrictions on the search space.

Diversity Evolutionary Algorithms

Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing

no code implementations10 May 2018 Zhe Li, Ji Li, Ao Ren, Caiwen Ding, Jeffrey Draper, Qinru Qiu, Bo Yuan, Yanzhi Wang

Recently, Deep Convolutional Neural Network (DCNN) has achieved tremendous success in many machine learning applications.

Learning Topics using Semantic Locality

no code implementations11 Apr 2018 Ziyi Zhao, Krittaphat Pugdeethosapol, Sheng Lin, Zhe Li, Caiwen Ding, Yanzhi Wang, Qinru Qiu

The topic modeling discovers the latent topic probability of the given text documents.

Topic Models

Efficient Recurrent Neural Networks using Structured Matrices in FPGAs

no code implementations20 Mar 2018 Zhe Li, Shuo Wang, Caiwen Ding, Qinru Qiu, Yanzhi Wang, Yun Liang

Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations.

Model Compression Time Series +1

C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing

no code implementations20 Mar 2018 Zhe Li, Xiaolong Ma, Hongjia Li, Qiyuan An, Aditya Singh Rathore, Qinru Qiu, Wenyao Xu, Yanzhi Wang

It is of vital importance to enable 3D printers to identify the objects to be printed, so that the manufacturing procedure of an illegal weapon can be terminated at the early stage.

Action Detection Activity Detection +1

C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs

no code implementations14 Mar 2018 Shuo Wang, Zhe Li, Caiwen Ding, Bo Yuan, Yanzhi Wang, Qinru Qiu, Yun Liang

The previous work proposes to use a pruning based compression technique to reduce the model size and thus speedups the inference on FPGAs.

A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection

no code implementations25 Feb 2018 Kun Hu, Zhe Li, Ying Liu, Luyin Cheng, Qi Yang, Yan Li

In the first prediction part, we focus on predicting the downward trend, which is an earlier stage of the customer lifecycle compared to churn.

Causal Inference Management +1

Image Dataset for Visual Objects Classification in 3D Printing

no code implementations15 Feb 2018 Hongjia Li, Xiaolong Ma, Aditya Singh Rathore, Zhe Li, Qiyuan An, Chen Song, Wenyao Xu, Yanzhi Wang

The rapid development in additive manufacturing (AM), also known as 3D printing, has brought about potential risk and security issues along with significant benefits.

Classification General Classification

An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing

no code implementations3 Feb 2018 Xiaolong Ma, Yi-Peng Zhang, Geng Yuan, Ao Ren, Zhe Li, Jie Han, Jingtong Hu, Yanzhi Wang

However, in these works, the memory design optimization is neglected for weight storage, which will inevitably result in large hardware cost.

Thoracic Disease Identification and Localization with Limited Supervision

1 code implementation CVPR 2018 Zhe Li, Chong Wang, Mei Han, Yuan Xue, Wei Wei, Li-Jia Li, Li Fei-Fei

Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning.

General Classification

A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer

no code implementations9 Sep 2017 Tianbao Yang, Zhe Li, Lijun Zhang

In this paper, we present a simple analysis of {\bf fast rates} with {\it high probability} of {\bf empirical minimization} for {\it stochastic composite optimization} over a finite-dimensional bounded convex set with exponential concave loss functions and an arbitrary convex regularization.

SEP-Nets: Small and Effective Pattern Networks

no code implementations13 Jun 2017 Zhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang

By doing this, we show that previous deep CNNs such as GoogLeNet and Inception-type Nets can be compressed dramatically with marginal drop in performance.

Binarization Quantization

A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning

no code implementations13 Mar 2017 Ning Liu, Zhe Li, Zhiyuan Xu, Jielong Xu, Sheng Lin, Qinru Qiu, Jian Tang, Yanzhi Wang

Automatic decision-making approaches, such as reinforcement learning (RL), have been applied to (partially) solve the resource allocation problem adaptively in the cloud computing system.

Cloud Computing Decision Making +4

Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks

no code implementations12 Mar 2017 Ji Li, Zihao Yuan, Zhe Li, Caiwen Ding, Ao Ren, Qinru Qiu, Jeffrey Draper, Yanzhi Wang

Recently, Deep Convolutional Neural Networks (DCNNs) have made unprecedented progress, achieving the accuracy close to, or even better than human-level perception in various tasks.

Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank

no code implementations ICML 2017 Liang Zhao, Siyu Liao, Yanzhi Wang, Zhe Li, Jian Tang, Victor Pan, Bo Yuan

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.

SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing

no code implementations18 Nov 2016 Ao Ren, Ji Li, Zhe Li, Caiwen Ding, Xuehai Qian, Qinru Qiu, Bo Yuan, Yanzhi Wang

Stochastic Computing (SC), which uses bit-stream to represent a number within [-1, 1] by counting the number of ones in the bit-stream, has a high potential for implementing DCNNs with high scalability and ultra-low hardware footprint.

Unified Convergence Analysis of Stochastic Momentum Methods for Convex and Non-convex Optimization

no code implementations12 Apr 2016 Tianbao Yang, Qihang Lin, Zhe Li

This paper fills the gap between practice and theory by developing a basic convergence analysis of two stochastic momentum methods, namely stochastic heavy-ball method and the stochastic variant of Nesterov's accelerated gradient method.

Improved Dropout for Shallow and Deep Learning

no code implementations NeurIPS 2016 Zhe Li, Boqing Gong, Tianbao Yang

To exhibit the optimal dropout probabilities, we analyze the shallow learning with multinomial dropout and establish the risk bound for stochastic optimization.

Deep Learning Stochastic Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.